Text Generation
Transformers
Safetensors
mixtral
yi
Mixture of Experts
conversational
text-generation-inference
4-bit precision
bitsandbytes
Instructions to use cloudyu/60B-MoE-Coder-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cloudyu/60B-MoE-Coder-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cloudyu/60B-MoE-Coder-v2") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cloudyu/60B-MoE-Coder-v2") model = AutoModelForCausalLM.from_pretrained("cloudyu/60B-MoE-Coder-v2") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use cloudyu/60B-MoE-Coder-v2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cloudyu/60B-MoE-Coder-v2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cloudyu/60B-MoE-Coder-v2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cloudyu/60B-MoE-Coder-v2
- SGLang
How to use cloudyu/60B-MoE-Coder-v2 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "cloudyu/60B-MoE-Coder-v2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cloudyu/60B-MoE-Coder-v2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "cloudyu/60B-MoE-Coder-v2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cloudyu/60B-MoE-Coder-v2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cloudyu/60B-MoE-Coder-v2 with Docker Model Runner:
docker model run hf.co/cloudyu/60B-MoE-Coder-v2
Upload folder using huggingface_hub
Browse files- config.json +46 -0
- generation_config.json +7 -0
- model-00001-of-00008.safetensors +3 -0
- model-00002-of-00008.safetensors +3 -0
- model-00003-of-00008.safetensors +3 -0
- model-00004-of-00008.safetensors +3 -0
- model-00005-of-00008.safetensors +3 -0
- model-00006-of-00008.safetensors +3 -0
- model-00007-of-00008.safetensors +3 -0
- model-00008-of-00008.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +50 -0
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "cloudyu/4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MixtralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 7168,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 20480,
|
| 14 |
+
"max_position_embeddings": 200000,
|
| 15 |
+
"model_type": "mixtral",
|
| 16 |
+
"num_attention_heads": 56,
|
| 17 |
+
"num_experts_per_tok": 2,
|
| 18 |
+
"num_hidden_layers": 60,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"num_local_experts": 2,
|
| 21 |
+
"output_router_logits": false,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"quantization_config": {
|
| 25 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 26 |
+
"bnb_4bit_quant_type": "fp4",
|
| 27 |
+
"bnb_4bit_use_double_quant": false,
|
| 28 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 29 |
+
"llm_int8_has_fp16_weight": false,
|
| 30 |
+
"llm_int8_skip_modules": null,
|
| 31 |
+
"llm_int8_threshold": 6.0,
|
| 32 |
+
"load_in_4bit": true,
|
| 33 |
+
"load_in_8bit": false,
|
| 34 |
+
"quant_method": "bitsandbytes"
|
| 35 |
+
},
|
| 36 |
+
"rms_norm_eps": 1e-05,
|
| 37 |
+
"rope_scaling": null,
|
| 38 |
+
"rope_theta": 5000000.0,
|
| 39 |
+
"router_aux_loss_coef": 0.001,
|
| 40 |
+
"sliding_window": null,
|
| 41 |
+
"tie_word_embeddings": false,
|
| 42 |
+
"torch_dtype": "bfloat16",
|
| 43 |
+
"transformers_version": "4.37.2",
|
| 44 |
+
"use_cache": true,
|
| 45 |
+
"vocab_size": 64000
|
| 46 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.37.2"
|
| 7 |
+
}
|
model-00001-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7728c4f085ca8ebdb4f4d26a8c2667ff11f03f0bd29bc127cea1a33af46fa72d
|
| 3 |
+
size 4997048702
|
model-00002-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42c9dc80930e5880fe2b2abd8b5942ae7aee0eb3ec3e358756355271b35e413e
|
| 3 |
+
size 4971434636
|
model-00003-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8daebd4babcdc2079b856283955b9476f4e0458de8bf6fa26eb94dc667eaddb0
|
| 3 |
+
size 4987939284
|
model-00004-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23936d6beec106080d427b1b241c2490ffd1a4387a0359517110e6cc68bff0c7
|
| 3 |
+
size 4971405852
|
model-00005-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:640b0fb15aead3872dec07239b35faf1190b76bf55acab643ef4a2635d4f1f10
|
| 3 |
+
size 4971434764
|
model-00006-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e64c97e7e7da1b673e33d09f9e27643e62a664e5444ddba50761d92badb6db08
|
| 3 |
+
size 4971434764
|
model-00007-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36e36fe2607dcf177a8c978144eb649c3774fd917bc6b351470bef7805c694e1
|
| 3 |
+
size 4740225534
|
model-00008-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:deda4a6e8ccb66230402c2f9ffffe66e02e2193f311d22ef80661b2c94aa2692
|
| 3 |
+
size 917504128
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"device_map": "cpu",
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"max_length": null,
|
| 37 |
+
"model_max_length": 1024,
|
| 38 |
+
"pad_to_multiple_of": null,
|
| 39 |
+
"pad_token": "<s>",
|
| 40 |
+
"pad_token_type_id": 0,
|
| 41 |
+
"padding_side": "left",
|
| 42 |
+
"sp_model_kwargs": {},
|
| 43 |
+
"spaces_between_special_tokens": false,
|
| 44 |
+
"stride": 0,
|
| 45 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 46 |
+
"truncation_side": "right",
|
| 47 |
+
"truncation_strategy": "longest_first",
|
| 48 |
+
"unk_token": "<unk>",
|
| 49 |
+
"use_default_system_prompt": false
|
| 50 |
+
}
|